Training method and device of data enhancement model
A training method and model technology, applied in the computer field, can solve problems such as inability to train natural language processing task models and general generation effects
Pending Publication Date: 2020-11-10
PING AN TECH (SHENZHEN) CO LTD
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the generation effects of these data enhancement methods are average, and the generated text is almost the same as the original text, which means that the original text has not been enhanced and expanded too much, so it is impossible to train high-precision natural language processing by using these texts. task model
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with aspects of the invention as recited in the appended claims.
[0038] The terminology used in the present invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein and in the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as use...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a training method and device of a data enhancement model and the method comprises the steps: inputting first corpus data into a first seq2seq model to obtain second corpus data, and inputting the second corpus data into a second seq2seq model to obtain third corpus data; respectively inputting the first corpus data and the third corpus data into a text classification modelfor identification to obtain a classification result; calculating a loss value according to a classification result, and optimizing parameters of the three models by utilizing the loss value; and performing loop iteration until a preset termination condition is met. As training of the text classification model and the data enhancement model is a game process, the training purpose of the text classification model is to enable the generated new corpus not to be easily distinguished by the text classification model, and the training purpose of the data enhancement model is to accurately distinguish whether the new corpus is the original corpus or the generated new corpus. Therefore, the corpus with a better effect can be generated by the data enhancement model, and the purpose of truly enhancing and expanding the original corpus is achieved.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to a training method and device for a data enhancement model. Background technique [0002] Data augmentation (Data Augmentation) is a technique to expand the training data set by allowing limited data to generate more equivalent data. It is an effective means to overcome the lack of training data and is currently widely used in various fields of deep learning. In the field of natural language processing, since natural language itself is a discrete abstract symbol, small changes may lead to huge deviations in meaning, so the data enhancement algorithm of natural language is worthy of our in-depth study. [0003] At present, commonly used natural language data enhancement methods include back translation using translation tools, synonym replacement or insertion, random deletion of words, addition of noise words, and word position transformation. However, the generation effects of...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F40/289G06K9/62G06N3/04G06N3/08
CPCG06F40/289G06N3/08G06N3/045G06F18/24
Inventor 郑立颖徐亮
Owner PING AN TECH (SHENZHEN) CO LTD